© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40742
    Prev
    Next
    INDEX
    Explanations

    makefile, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    侥幸
    -0.30
    å®īæħ°
    -0.27
    ниÑĨ
    -0.27
    éĽĢ
    -0.26
    antino
    -0.26
    \Base
    -0.25
    æķħäºĭ
    -0.24
    SIDE
    -0.24
    é©Ń
    -0.24
    å±±åĮº
    -0.24
    POSITIVE LOGITS
    yz
    0.29
    iado
    0.26
    oz
    0.25
    thy
    0.25
    ä¸ĬéŨ
    0.24
    ign
    0.24
     continued
    0.24
     troch
    0.24
    åĴĮ社ä¼ļ
    0.24
     objected
    0.23
    Activations Density 0.984%

    No Known Activations